File: unsupported-option-gpu.c

package info (click to toggle)
llvm-toolchain-20 1%3A20.1.8-1~exp1
  • links: PTS, VCS
  • area: main
  • in suites: experimental
  • size: 2,111,388 kB
  • sloc: cpp: 7,438,767; ansic: 1,393,871; asm: 1,012,926; python: 241,728; f90: 86,635; objc: 75,411; lisp: 42,144; pascal: 17,286; sh: 10,027; ml: 5,082; perl: 4,730; awk: 3,523; makefile: 3,349; javascript: 2,251; xml: 892; fortran: 672
file content (6 lines) | stat: -rw-r--r-- 444 bytes parent folder | download | duplicates (16) 
1
2
3
4
5
6
 
/// Some target-specific options are ignored for GPU, so %clang exits with code 0.
// DEFINE: %{check} = %clang -### --target=x86_64-linux-gnu -c -mcmodel=medium

// RUN: %{check} -x cuda %s --cuda-path=%S/Inputs/CUDA/usr/local/cuda --offload-arch=sm_60 --no-cuda-version-check -fbasic-block-sections=all
// RUN: %{check} -x hip %s --offload=spirv64 -nogpulib -nogpuinc
// RUN: %{check} -x hip %s --rocm-path=%S/Inputs/rocm -nogpulib -nogpuinc